search

ratishsp / data2text-plan-py

Code for AAAI 2019 paper on Data-to-Text Generation with Content Selection and Planning
163 stars 46 forks source link

How to generate the content selection in a more difficult scenario? #35

Closed happycjksh closed 3 years ago

happycjksh commented 3 years ago

I have a dataset that also needs content selection. But the table values don't match with summary tokens. For example, in the table, the value is "4993 million", but in the summary, the value is expressed as 2.5 billion. In the scenario, I can't use string matching to generate content selection and planning. Could you give me some advice about the problem?

ratishsp commented 3 years ago

The copy mechanism will work in an exact string match. In other cases, the model will attend on the table and predict from the output vocabulary.